Data engineering MCP servers

A server here data pipelines, ETL, data warehouses, data quality or data catalogs.

Not here: querying a single database.

386servers
205 remote181 localTagged by Odel's AI, which can make mistakes

Best fit

191 made for this, ranked by starsRemoteLocal
  1. ZTDS @moxno/ztdsOpen standard MCP server for Zero-Trust Data Sanitization (ZTDS RFC v1.0). In-memory PII masking.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  2. Census MCP by usefulapi @usefulapi/censusList reverse-ETL sources, destinations, models, syncs and runs; trigger syncs into SaaS tools.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  3. Notanda (Beta) @rudiregenwurm/notandaEvery OpenAlex search stores its request, response and checksums so sources can be checked later.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  4. Attesta @doralboim/attestaProvenance-grade Portugal residential property data and signed JWS verification for AI agents.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  5. letin: Power Query (M) @s-curvelabs/letinInspect, refactor, lint, run and version Power Query (M) in Excel workbooks and Power BI projects.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  6. Sparkforensics @shuffle-works/sparkforensics-mcpMCP server for diagnosing Apache Spark event-log performance issues and comparing runs.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  7. Segment @pipeworx-io/segmentSegment MCP Pack — wraps the Segment Public API (https://api.segmentapis.com).7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  8. Dataset Aggregate & Pivot @nero-engine/dataset-aggregate-pivotGROUP BY and pivot tables for JSON rows: 11 functions, date buckets, top N, totals, messy numbers.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  9. Dataset Cleaner & Exporter @nero-engine/dataset-cleaner-exporterDedupe, flatten and clean messy JSON rows (emails, phones, URLs, HTML) in one call, as JSON or CSV.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  10. BigQuery Data Platform @debilla/data-platform-mcpRead-only BigQuery tools for plain-language data questions, with a cost gate on every query3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  11. JoinLayer @joinlayer/mcpOperate secure JoinLayer data pipelines through delegated OAuth.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  12. ClinicMarketIQ Public Data @evgeniy-yudin/clinicmarketiq-public-dataRead-only U.S. healthcare dataset metadata, schemas, immutable downloads, and checksums.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  13. DLMS Bridge @csoai-org/dlms-bridge-mcpBridge DLMS/COSEM smart-meter + energy data to ONE OS — parse, map, govern (IEC 62056 / NIS2 /5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  14. Inflectiv @inflectiv/inflectiv-mcp-serverSearch, build and manage Inflectiv datasets and AI agents, plus ChainAware on-chain intelligence.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  15. Analytixus @analytixus/analytixus-mcpAnalytixus DnAML repository access (read/write nodes, tree navigation, search) via MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.
  16. Data Cleaner Agent @wesseltl/data-cleaner-agentClean messy CSVs: an LLM picks the steps, tested code does the work. Data untouched by the model.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  17. AEP @focusgts/aepFull-CRUD server for AEP, Journey Optimizer and CJA. 61 tools from one OAuth credential.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  18. EuroRWA Analyst @crytobot459/eurorwa-analystEuroRWA analyst: tokenized money-market fund signals, snapshots, analytics and alerts.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  19. datadiffer @gauthierpiarrette/datadifferRead-only table diffs with segment attribution: which slice of your data changed.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  20. Pbix Atlas @fabienfrfr/pbix-atlasBidirectional data lineage graph for Power BI (.pbix) files, from source to display4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  21. Pbix Lineage @fabienfrfr/pbix-lineageBidirectional data lineage graph for Power BI (.pbix) files, from source to display4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  22. Public Data Catalog @yhay81/public-data-catalogReviewed public-data search and execution with provenance and verifiable integrity receipts.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  23. PixLint @amitsingh-24/pixlintLint, curate & prepare computer-vision datasets from your AI assistant — MCP server, 67 tools4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  24. Interzoid MCP @interzoid/mcp-server58 AI data quality, data matching, and data enrichment APIs for better data ROI5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.